US9958531B2 - Determining a location of a wireless device using fingerprinting - Google Patents
Determining a location of a wireless device using fingerprinting Download PDFInfo
- Publication number
- US9958531B2 US9958531B2 US15/165,338 US201615165338A US9958531B2 US 9958531 B2 US9958531 B2 US 9958531B2 US 201615165338 A US201615165338 A US 201615165338A US 9958531 B2 US9958531 B2 US 9958531B2
- Authority
- US
- United States
- Prior art keywords
- values
- difference
- signal
- fingerprint
- query
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
- G01S5/02521—Radio frequency fingerprinting using a radio-map
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
Definitions
- wireless devices can include Global Positioning System (GPS) receivers that can be used to perform satellite-based positioning of the wireless devices.
- GPS Global Positioning System
- GPS-based positioning techniques may not be effective in an indoor environment or in a dense urban environment, where satellite signals may be attenuated.
- FIG. 1 is a block diagram of an example network arrangement in which a fingerprint-based positioning technique can be implemented, in accordance with some implementations.
- FIGS. 2A-2B are flow diagrams of example positioning techniques, according to some implementations.
- FIG. 3 is a flow diagram of another example positioning technique, according to alternative implementations.
- FIG. 4 is a block diagram of a wireless device according to some implementations.
- a wireless device can refer to an electronic device that is able to communicate wirelessly with another device.
- wireless devices include a smartphone, a tablet computer, a notebook computer, a wearable device (e.g. smart watch, smart eyeglasses, etc.), a vehicle, a game appliance, or any other electronic device that is able to communicate wirelessly.
- a wireless device can also be referred to as a mobile device, since it is able to move around to different locations.
- a wireless device does not have to be mobile during use, but rather can be provided at a fixed location, such as a desktop computer, a server computer, a communication node, and so forth.
- Wireless devices can be positioned based on wireless signals transmitted by a wireless network infrastructure, such as a wireless local area network (WLAN) that operates using WI-FI or other wireless protocols.
- WLAN wireless local area network
- Examples of other wireless technologies include the Bluetooth technology, the Ultra-Wideband (UWB) technology, a cellular technology such as the Long-Term Evolution (LTE) or Evolved Universal Mobile Telecommunications System Terrestrial Radio Access (E-UTRA) technology, and so forth.
- LTE Long-Term Evolution
- E-UTRA Evolved Universal Mobile Telecommunications System Terrestrial Radio Access
- a wireless network infrastructure includes an arrangement of wireless access network nodes that are used by wireless devices to communicate with each other or with other endpoint devices.
- a wireless device can establish a wireless connection with a wireless access network node to allow traffic data of the wireless device to be carried over the wireless connection.
- a fingerprinting technique can be used for determining a location of a wireless device based on wireless signals transmitted by the wireless network infrastructure.
- Specific examples of fingerprinting techniques include WI-FI fingerprinting techniques.
- WI-FI fingerprinting techniques Although the present disclosure refers to examples in which WI-FI fingerprinting techniques are used, it is noted that in other examples, other fingerprinting techniques based on use of other types of wireless signaling can be employed.
- FIG. 1 illustrates an example of a network arrangement that includes wireless access points (APs) 102 that are able to communicate wirelessly with a wireless device, such as wireless device 104 .
- APs wireless access points
- FIG. 1 illustrates an example of a network arrangement that includes wireless access points (APs) 102 that are able to communicate wirelessly with a wireless device, such as wireless device 104 .
- APs wireless access points
- FIG. 1 illustrates an example of a network arrangement that includes wireless access points (APs) 102 that are able to communicate wirelessly with a wireless device, such as wireless device 104 .
- APs wireless access points
- the APs 102 can be wireless access network nodes that are part of a WLAN that operates according to the WI-FI technology.
- the WI-FI technology is described by the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards.
- the APs can refer to other types of wireless access nodes that employ other wireless technologies to communicate with wireless devices.
- a fingerprinting technique or mechanism used to position wireless devices can define specific locations (represented by circles in FIG. 1 ) at which fingerprints are collected. These locations (represented by circles in FIG. 1 ) can be referred to as “training locations” or “fingerprint locations.” In the example of FIG. 1 , the fingerprint locations are generally arranged in a rectangular grid within a given area. In other examples, fingerprint locations can have other arrangements.
- a fingerprint can refer to a collection (e.g. vector) of signal values detected at a specific fingerprint location, where the signal values are received at the specific fingerprint location by at least one wireless device from the APs 102 .
- respective signal values from the different APs 102 can be detected. For example, in FIG. 1 , assuming that there are three APs, then at least one wireless device at a given fingerprint location can observe a first signal value from a first AP, a second signal value from a second AP, and a third signal value from a third AP.
- the first, second, and third signal values form a collection of signal values that make up a fingerprint for the given fingerprint location. If there are more APs in the network arrangement, then the collection of signal values collected for each fingerprint location can include more signal values for the additional APs.
- the signal values that can be observed can represent strengths of wireless signals between the at least one wireless device and the APs 102 .
- An example of a signal strength value is a Received Signal Strength Indicator (RSSI), which provides a measurement of power present in a received radio signal.
- RSSI Received Signal Strength Indicator
- other indications of signal strength can be employed, such as a value representing a signal-to-noise ratio (SNR), a measurement of signal power, a measurement of signal quality, or any other type of indication from which a signal strength can be derived or inferred.
- the signal values can include information representing a round-trip time (RTT) or another time measure that represents a time of communicating a signal between a wireless device and an AP. The RTT is the total time for a signal to travel from a first device to a second device and back to the first device.
- RTT round-trip time
- fingerprints that include signal values that represent strengths of signals.
- fingerprints can additionally or alternatively include signal values that include time measures, where such time measures that are part of fingerprints can be used to determine a location of a wireless device.
- Fingerprints for the different fingerprint locations can be determined during a training phase, when one or more wireless devices can be moved around to the different fingerprint locations to measure signal values from the APs 102 .
- Signal values from the APs are detected by the wireless device(s) during the training phase, and these signal values are provided by the wireless device(s) to a system 106 to develop the fingerprints that are stored in a fingerprint database.
- the fingerprint database is used by system 106 to perform positioning of a wireless device, or alternatively, the fingerprint database is communicated by the system 106 to other device(s) to perform the positioning of a wireless device.
- the multiple devices at a particular fingerprint location can each measure its respective collection of signal values from the different APs 102 .
- the fingerprint for a given fingerprint location would be the aggregate of signal values acquired by the multiple wireless devices (at the given fingerprint location) for each AP, where the aggregate can be a mean, a median, a minimum, a maximum, a sum, or some other type of aggregate.
- wireless device 1 can acquire a first collection of signal values [s 1 _ a , s 1 _ b , s 1 _ c ], where s 1 _ a is received by wireless device 1 from a first AP (a), s 1 _ b is received by wireless device 1 from a second AP (b), and s 1 _ c is received by wireless device 1 from a third AP (c).
- wireless device 2 can acquire a second collection of signal values [s 2 _ a , s 2 _ b , s 2 _ c ], and wireless device 3 can acquire a first collection of signal values [s 3 _ a , s 3 _ b , s 3 _ c ].
- the fingerprint [da, db, dc] for the fingerprint location can then be computed by aggregating [s 1 _ a , s 1 _ b , s 1 _ c ], [s 2 _ a , s 2 _ b , s 2 _ c ], and [s 3 _ a , s 3 _ b , s 3 _ c ], where da is an aggregate (e.g.
- a fingerprint at a given location is computed from a set of WI-FI scans collected at or near the given location from one or more wireless devices.
- the fingerprint is the aggregate signal value of the RSSI (or other signal value) of each observed AP across all the scans collected at or near the given location.
- the aggregate can be mean or median or mode.
- the fingerprint at the given location contains value ⁇ 67 (mean of ⁇ 64, ⁇ 67, ⁇ 69) and value ⁇ 50 (mean of ⁇ 45, ⁇ 50, ⁇ 50, ⁇ 53).
- the determination of a fingerprint at the different fingerprint locations can be determined using just one wireless device.
- the signal values acquired by the wireless device(s) at each fingerprint location during the training phase are communicated to the system 106 , which can include a computer or an arrangement of computers.
- the system 106 includes a processor 108 (or multiple processors), and a non-transitory machine-readable or computer-readable storage medium 110 that can store fingerprint determination instructions 112 .
- a processor can include a microprocessor, a microcontroller, a programmable integrated circuit, a programmable gate array, or another hardware processing circuit.
- the fingerprint determination instructions are machine-readable instructions that are executable on the processor(s) 108 to determine fingerprints for the different fingerprint locations based on the received signal values acquired by the wireless device(s) during the training phase.
- the generated fingerprints are stored by the fingerprint determination instructions 112 in a fingerprint database 114 .
- the fingerprint database 114 includes the fingerprints and indications of respective fingerprint locations for the fingerprints.
- the fingerprint database 114 can be used for determining the location of a wireless device, such as the wireless device 104 during operation of the wireless device 104 . Positioning wireless devices using the fingerprint database 114 can be performed during a “location phase,” which is distinct from the training phase.
- the wireless device 104 can receive signal values from the respective APs 102 .
- the wireless device 104 can send a location query that includes the received signal values to the system 106 to cause the system 106 to determine the location of the wireless device 104 .
- location determination instructions 116 are executable on the processor(s) 108 to compare the collection of signal values received from the wireless device 104 to the fingerprint database 114 . Based on matching the received collection of signal values in the location query from the wireless device 104 to a fingerprint in the fingerprint database 114 , the location determination instructions 116 can estimate the location of the wireless device 104 , and the determined location can be communicated back to the wireless device 104 as a response to the location query.
- the location determination can be performed by a different system, such as by an AP 102 , or by the wireless device 104 itself.
- the fingerprint database 114 can be communicated to the APs 102 or the wireless device 104 for use at the APs 102 or the wireless device 104 to perform location determination based on fingerprint matching.
- the wireless device(s) used during the training phase may have different characteristics from the wireless device (e.g. 104 ) whose location is to be determined during the location phase.
- the different characteristics of the wireless devices can be due to hardware differences, such as the difference between hardware of a tablet computer and a smartphone, for example. More generally, different types of wireless devices may have different hardware, which can cause them to detect signal values from the APs 102 differently.
- the different hardware can be due to differences in orientation and arrangement of radio antennas, the sensitivities of wireless interface circuits, and/or a behavior of signal drivers in the wireless interface circuits. For example, a first type of wireless device can detect a first RSSI from a first AP at a first location, while a second type of wireless device can detect a second, different RSSI from the first AP at the same first location.
- different characteristics of the wireless devices that can cause the wireless devices at the same location to detect different signal values from the same AP can be due to different software or firmware running on the wireless devices. If a first wireless device has different characteristics from a second wireless device, then the first wireless device can measure different RSSI values than the second wireless device at the exact same location. As a result, comparing raw signal values from two different wireless devices that have different characteristics can result in positioning errors when using a fingerprint technique.
- a rank-based signal value difference technique can be employed, where pre-processing based on ranking of signal values received by a wireless device is applied prior to matching the signal values to fingerprints in the fingerprint database 114 .
- a corresponding difference deviation technique can be used that applies post-processing to differences calculated between received signal values and fingerprints in the fingerprint database 114 .
- a combination of the rank-based signal difference technique and the corresponding difference deviation technique can be used.
- FIG. 2A is a flow diagram of an example process according to the rank-based signal value difference technique.
- the process of FIG. 2A can be performed by the location determination instructions 116 in the system 106 .
- the process of FIG. 2A can be performed by an AP 102 or by the wireless device 104 whose location is to be determined.
- the process of FIG. 2A includes receiving (at 202 ) a query including signal values representing strengths of signals between a first wireless device (e.g. wireless device 104 ) and corresponding APs 102 .
- the signal values can be RSSIs received from the respective APs by the first wireless device.
- the signal values can be computed by the wireless device 104 or by another entity based on signals from the APs detected by the wireless device 104 .
- the query can include signal values that provide time measures (e.g. RTT) of signals between the first wireless device and the corresponding APs 102 . The time measures can be in place of or in addition to representations of strengths of the signals. More generally, a query can include signal values that provide measures (e.g. strength measures and/or time measures) of signals between the first wireless device and the corresponding APs 102 .
- the process includes ranking (at 204 ) the APs for the query based on sorting the signal values in the query.
- the sorting of the signal values arranges the signal values in a sequence of signal values based on which signal values are greater or less than other signal values. For example, the sorting can arrange the signal values in descending order.
- Arranging signal values in descending order refers to arranging the highest signal value first in sequence and the lowest signal value last in the sequence.
- the process of FIG. 2A further includes computing (at 206 ), using the ranking, similarity values between the query and respective fingerprints of signal values collected at multiple fingerprint locations in an area (such as at the fingerprint locations shown in FIG. 1 ).
- Each signal value of the signal values in a fingerprint represents a strength (and/or a time measure) of a wireless signal between at least one wireless device at a fingerprint location and a respective AP. More generally, each signal value in a fingerprint provides a measure of a wireless signal between at least one wireless device at a fingerprint location and a respective AP.
- the process of FIG. 2A further determines (at 208 ) a location of the first wireless device based on the computed similarity values.
- Table 1 shows an example of signal values collected by the wireless device 104 whose location is to be determined—these signal values collected by the wireless device 104 are in the location query column of Table 1.
- Table 1 also includes a fingerprint 1 column and a fingerprint 2 column, which corresponds to fingerprints that are part of the fingerprint database 114 . It is assumed that just two fingerprints are in the fingerprint database 114 for purposes of this example.
- each row represents signal values collected from a respective AP.
- the first row includes signal values from AP A1 in the location query, fingerprint 1, and fingerprint 2, respectively;
- the second row includes signal values from AP A2 in the location query, fingerprint 1, and fingerprint 2, respectively; and so forth.
- the APs are ranked based on a sorted order (decreasing order) of the signal values.
- the rank of an AP for the location query or a fingerprint is the position of the AP in the sorted order.
- the sorted order for the location query is ⁇ A1, A2, A3, A4, A5, A6 ⁇ .
- AP A1 has rank 1
- AP A2 has rank 2, and so forth.
- the sorted order for fingerprint 1 is ⁇ A4, A3, A2, A1, A6, A5 ⁇
- the sorted order for fingerprint 2 is ⁇ A5, A1, A2, A3, A4, A6 ⁇ .
- the rank of AP A4 is 1 in fingerprint 1, and 5 in fingerprint 2.
- outliers can be omitted or changed in value.
- a maximum value for RSSI can be set; any RSSI value higher than the maximum value can be changed to the maximum value.
- the signal values for the top k (k>1) APs are used—the signal values for the remaining APs are ignored.
- fingerprint 1 After the APs have been ranked for each of the location query, fingerprint 1, and fingerprint 2,
- the rank-based signal value difference is represented as a similarity vector of difference values, where each difference value is a measure (expressed as a numeric value or as a different representation) of a difference between a value in a first vector and a corresponding value in a second vector.
- the second vector includes a re-ordered collection of signal values of fingerprint k, where the re-ordering of signal values in the second vector is based on the ranking of APs for the location query. More specifically, given the location query and fingerprint k, the similarity vector between the location query and fingerprint k is computed as follows.
- the i-th element of the similarity vector is defined as the difference in the signal value (e.g. RSSI) between AP-i and the j-th ranked AP in fingerprint k, where j is the rank of AP-i for the location query.
- vector 1 is fingerprint 1
- vector 2 is a re-ordered collection of the signal values of fingerprint 1 based on the ranking of APs for the location query.
- the re-ordering of the signal values of fingerprint 1 is based on the ranking of APs for the location query includes arranging the signal values of fingerprint 1 in order from highest ranked AP to lowest ranked AP.
- the signal value of AP A1 in fingerprint 1 is ⁇ 48
- the rank of AP A1 for the location query is 1
- the signal value of the AP with rank 1 in fingerprint 1 is ⁇ 43.
- the first element in vector 2 is ⁇ 43
- vector 1 for fingerprint 1 is represented as follows: [RSSI(A1),RSSI(A2),RSSI(A3),RSSI(A4),RSSI(A5),RSSI(A6)].
- Vector 2 for fingerprint 1 is represented as follows: [RSSI(A4),RSSI(A3),RSSI(A2),RSSI(A1),RSSI(A5),RSSI(A6)].
- the first rank-based signal value difference (e.g. rank-based similarity vector) between fingerprint 1 and the location query is computed as: [RSSI(A1),RSSI(A2),RSSI(A3),RSSI(A4),RSSI(A5),RSSI(A6)] ⁇ [RSSI(A4),RSSI(A3),RSSI(A2),RSSI(A1),RSSI(A5),RSSI(A6)].
- a similarity measure (e.g. a numeric value or other type of representation) can be calculated in a number of different ways.
- ⁇ i 1 n ⁇ ⁇ e - ( d i / h ) 2 , where h is a smoothing parameter.
- Different Gaussian similarity values represent different degrees of similarity between the location query and the respective fingerprints.
- the estimated position of the wireless device 104 is defined as the weighted centroid of the fingerprint locations, where the weights are the similarity values. In other examples, other techniques for determining the location of the wireless device 104 using the similarity values can be employed.
- similarity measures can be used based on the rank-based similarity vector computed from determining the difference between a fingerprint and a location query.
- a similarity measure based on a Gaussian kernel can be used.
- FIG. 2B is a flow diagram of an example process according to further implementations.
- the process of FIG. 2B can be performed by the location determination instructions 116 in the system 106 .
- the process of FIG. 2B can be performed by an AP 102 or by the wireless device 104 whose location is to be determined.
- the process of FIG. 2B includes receiving (at 222 ) a query including signal values representing strengths (and/or time measures) of signals between a first wireless device (e.g. wireless device 104 ) and corresponding APs 102 .
- the query can include identifiers of the APs detected by the first wireless device, where the identifiers can be Medium Access Control (MAC) addresses or other types of identifiers.
- MAC Medium Access Control
- the process of FIG. 2B includes retrieving (at 224 ), from a fingerprint database (e.g. 114 in FIG. 1 ), a relevant set of fingerprints based on the identifiers of the APs in the query.
- a fingerprint database e.g. 114 in FIG. 1
- Each fingerprint can also include identifiers of APs for which signal values have been collected in the fingerprint.
- the relevant set of fingerprints can be a subset less than all of the fingerprints in the fingerprint database.
- the fingerprints in the subset are those fingerprints that include identifiers of APs matching the identifiers of APs in the query.
- the process of FIG. 2B further includes ranking (at 226 ) the APs for the query based on sorting the signal values in the query.
- the process of FIG. 2B includes computing (at 228 ), using the ranking of the APs, rank-based similarity vectors between the query and respective fingerprints.
- the process of FIG. 2B further includes computing (at 230 ), based on the rank-based similarity vectors, similarity values between the query and respective fingerprints of signal values collected at multiple fingerprint locations in an area (such as at the fingerprint locations shown in FIG. 1 ).
- the process of FIG. 2B further determines (at 232 ) a location of the first wireless device based on the computed similarity values.
- FIG. 3 is a flow diagram of an example process that uses the corresponding difference deviation technique for determining a location of a wireless device.
- the process of FIG. 3 can be performed by the location determination instructions 116 executable in the system of FIG. 1 , in some examples, or the process of FIG. 3 can be performed by an AP 102 or the wireless device 104 whose location is to be derived.
- the process includes receiving (at 302 ) a query including signal values representing strengths (and/or time measures) of signals between a first wireless device and corresponding APs. These received signal values can be RSSIs or other indications.
- the process includes computing (at 304 ) a difference between the signal values in the query and a respective fingerprint of signal values (e.g. a fingerprint in the fingerprint database 114 of FIG. 1 ) representing strengths (and/or time measures) of wireless signals between at least one wireless device at a respective fingerprint location and the corresponding APs, to output a respective collection of difference values.
- a respective fingerprint of signal values e.g. a fingerprint in the fingerprint database 114 of FIG. 1
- this can be the difference between the signal values of fingerprint 1 and the signal values of the location query.
- the process of FIG. 3 includes computing (at 306 ) an aggregate of the difference values in the respective collection of difference values, to output a respective aggregate value.
- the respective collection of difference values is in the form of [d 1 , d 2 , d 3 , d 4 , d 5 , d 6 ]
- an aggregate of the difference values in the respective collection is based on applying an aggregate function on d 1 , d 2 , d 3 , d 4 , d 5 , and d 6 .
- the applied aggregate can be a median, such that the median value of d 1 , d 2 , d 3 , d 4 , d 5 , and d 6 is computed.
- the aggregate can be a mean of d 1 , d 2 , d 3 , d 4 , d 5 , and d 6 , a maximum of d 1 , d 2 , d 3 , d 4 , d 5 , and d 6 , a minimum of d 1 , d 2 , d 3 , d 4 , d 5 , and d 6 , a sum of d 1 , d 2 , d 3 , d 4 , d 5 , and d 6 , or some other aggregate.
- the process of FIG. 3 then computes (at 308 ) an adjusted respective collection of difference values based on a difference between the respective collection of first difference values and the respective aggregate value.
- the respective aggregate value is represented as d median (which represents the median of d 1 -d 6 )
- the process of FIG. 3 determines (at 310 ) if the tasks 304 , 306 , and 308 are to be re-iterated for another fingerprint of signal values (e.g. another fingerprint in the fingerprint database 114 ). If so, then tasks 304 , 306 , and 308 are re-iterated for this other fingerprint of signal values.
- another fingerprint of signal values e.g. another fingerprint in the fingerprint database 114 .
- the process of FIG. 3 determines (at 312 ) a location of the first wireless device based on the respective adjusted collections of signal values produced by multiple iterations of task 308 .
- a similarity measure can be computed based each adjusted collection of difference values [d 1 ′, d 2 ′, d 3 ′, d 4 ′, d 5 ′, d 6 ′], such as based on a sum of absolute differences as discussed above or some other similarity determination technique.
- a combination of the rank-based signal difference technique and the corresponding difference deviation technique can be used.
- the sorting of the received signal values and the sorting of the collections of signal values can be performed, and then tasks 304 , 306 , and 308 can be applied on the sorted signal values.
- FIG. 4 is a block diagram of an example wireless device 104 , which includes a processor (or multiple processors) 400 , which can be coupled to a communication interface 402 to communicate wirelessly with an AP 102 , and a non-transitory machine-readable or computer-readable storage medium 404 that stores location determination instructions 406 that are executable on the processor(s) 400 .
- a processor or multiple processors
- FIG. 4 is a block diagram of an example wireless device 104 , which includes a processor (or multiple processors) 400 , which can be coupled to a communication interface 402 to communicate wirelessly with an AP 102 , and a non-transitory machine-readable or computer-readable storage medium 404 that stores location determination instructions 406 that are executable on the processor(s) 400 .
- the location determination instructions 406 can send a location query (that includes measured signal values such as RSSIs) to a remote system, such as the system 106 or an AP 102 , for the system 106 or the AP 102 to compare the signal values of the location query to fingerprints of a fingerprint database (e.g. 114 in FIG. 1 ) to determine the location of the wireless device 104 .
- the location determination instructions 406 can receive a response to the location query that includes an estimated location of the wireless device 104 .
- the location determination instructions 406 can be executed on the processor(s) 100 to compare the signal values measured by the wireless device 104 to fingerprints of the fingerprint database.
- the fingerprint database 114 is communicated from the system 106 to the wireless device 104 to allow the location determination instructions 406 to perform the comparison.
- Each of the storage media 110 ( FIG. 1 ) and 404 ( FIG. 4 ) can include one or multiple different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories; magnetic disks such as fixed, floppy and removable disks; other magnetic media including tape; optical media such as compact disks (CDs) or digital video disks (DVDs); or other types of storage devices.
- DRAMs or SRAMs dynamic or static random access memories
- EPROMs erasable and programmable read-only memories
- EEPROMs electrically erasable and programmable read-only memories
- flash memories such as fixed, floppy and removable disks
- magnetic media including tape such as compact disks (CDs) or digital video disks (DVDs); or other types of storage devices.
- CDs compact disks
- DVDs digital video disks
- Such computer-readable or machine-readable storage medium or media is (are) considered to be part of an article (or article of manufacture).
- An article or article of manufacture can refer to any manufactured single component or multiple components.
- the storage medium or media can be located either in the machine running the machine-readable instructions, or located at a remote site from which machine-readable instructions can be downloaded over a network for execution.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
Description
TABLE 1 | |||||
Access Point | Location Query | Fingerprint 1 | Fingerprint 2 | ||
A1 | −55 | −48 | −63 | ||
A2 | −56 | −46 | −65 | ||
A3 | −58 | −44 | −67 | ||
A4 | −61 | −43 | −74 | ||
A5 | −89 | −79 | −60 | ||
A6 | −91 | −78 | −80 | ||
-
- (1) a first rank-based signal value difference (including a first collection of difference values) is computed between the location query and fingerprint 1, and
- (2) a second rank-based signal value difference (including a second collection of difference values) is computed between the location query and fingerprint 2.
vector 1−vector 2=[−48,−46,−44,−43,−79,−78]−[−43,−44,−46,−48,−78,−79]=[−5,−2,2,5,−1,1].
[RSSI(A1),RSSI(A2),RSSI(A3),RSSI(A4),RSSI(A5),RSSI(A6)].
[RSSI(A4),RSSI(A3),RSSI(A2),RSSI(A1),RSSI(A5),RSSI(A6)].
[RSSI(A1),RSSI(A2),RSSI(A3),RSSI(A4),RSSI(A5),RSSI(A6)]−[RSSI(A4),RSSI(A3),RSSI(A2),RSSI(A1),RSSI(A5),RSSI(A6)].
[−63,−65,−67,−74,−60,−80]−[−60,−63,−65,−67,−74,−80]=[−3,−2,−2,−7,14,0].
where h is a smoothing parameter.
[d1−d median ,d2−d median ,d3−d median ,d4−d median ,d5−d median ,d6−d median ]=[d1′,d2′,d3′,d4′,d5′,d6′].
Claims (19)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/165,338 US9958531B2 (en) | 2016-05-26 | 2016-05-26 | Determining a location of a wireless device using fingerprinting |
PCT/CA2017/050628 WO2017201621A1 (en) | 2016-05-26 | 2017-05-24 | Determining a location of a wireless device using fingerprinting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/165,338 US9958531B2 (en) | 2016-05-26 | 2016-05-26 | Determining a location of a wireless device using fingerprinting |
Publications (2)
Publication Number | Publication Date |
---|---|
US20170343638A1 US20170343638A1 (en) | 2017-11-30 |
US9958531B2 true US9958531B2 (en) | 2018-05-01 |
Family
ID=60410991
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/165,338 Active US9958531B2 (en) | 2016-05-26 | 2016-05-26 | Determining a location of a wireless device using fingerprinting |
Country Status (2)
Country | Link |
---|---|
US (1) | US9958531B2 (en) |
WO (1) | WO2017201621A1 (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3266258B1 (en) * | 2015-03-09 | 2020-12-23 | Hewlett-Packard Enterprise Development LP | Predicting available access points |
JP6803559B2 (en) * | 2016-10-28 | 2020-12-23 | パナソニックIpマネジメント株式会社 | Position estimation method and program |
WO2018176511A1 (en) * | 2017-03-28 | 2018-10-04 | 华为技术有限公司 | Fingerprint locating method and related device |
US10600252B2 (en) * | 2017-03-30 | 2020-03-24 | Microsoft Technology Licensing, Llc | Coarse relocalization using signal fingerprints |
US10531065B2 (en) * | 2017-03-30 | 2020-01-07 | Microsoft Technology Licensing, Llc | Coarse relocalization using signal fingerprints |
US11287510B2 (en) * | 2018-01-16 | 2022-03-29 | Here Global B.V. | Client-based storing of tuning parameters for positioning services |
CN109257441B (en) * | 2018-10-31 | 2022-01-28 | 维沃移动通信有限公司 | Wireless local area network position acquisition method and device |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030064735A1 (en) * | 1998-09-22 | 2003-04-03 | Spain David Stevenson | Location determination using RF fingerprinting |
US20080285530A1 (en) * | 2004-05-18 | 2008-11-20 | Cisco Systems, Inc. | Wireless Node Location Mechanism Featuring Definition of Search Region to Optimize Location Computation |
US20130162481A1 (en) | 2009-10-01 | 2013-06-27 | Parviz Parvizi | Systems and methods for calibration of indoor geolocation |
US20130281130A1 (en) * | 2011-12-16 | 2013-10-24 | Rongzhen Yang | System and method for multi-radio cloud computing for location sensing |
US20140171114A1 (en) | 2012-12-14 | 2014-06-19 | Apple Inc. | Location determination using fingerprint data |
US20140179341A1 (en) | 2012-12-24 | 2014-06-26 | Jaroslaw J. Sydir | Geo-location signal fingerprinting |
US20140295878A1 (en) | 2012-05-01 | 2014-10-02 | Shao-Wen Yang | Simultaneous localization and mapping using spatial and temporal coherence for indoor location |
US20150087239A1 (en) | 2013-09-26 | 2015-03-26 | Xue Yang | Techniques for cross-device radio signal strength calibration |
US20150133148A1 (en) | 2013-05-21 | 2015-05-14 | Intel Corporation | Systems and methods for simultaneously and automatically creating databases of wifi signal information |
US20150222372A1 (en) | 2014-02-05 | 2015-08-06 | Google Inc. | Methods and Systems for Determining Signal Strength Maps for Wireless Access Points Robust to Measurement Counts |
US20160018507A1 (en) | 2014-07-17 | 2016-01-21 | Verizon Patent And Licensing Inc. | Location tracking for a mobile device |
US20160033266A1 (en) | 2014-08-01 | 2016-02-04 | Google Inc. | Construction of a Surface of Best GPS Visibility From Passive Traces Using SLAM for Horizontal Localization and GPS Readings and Barometer Readings for Elevation Estimation |
US20160066151A1 (en) * | 2014-08-28 | 2016-03-03 | Qualcomm Incorporated | Selective crowdsourcing of location-related data |
-
2016
- 2016-05-26 US US15/165,338 patent/US9958531B2/en active Active
-
2017
- 2017-05-24 WO PCT/CA2017/050628 patent/WO2017201621A1/en active Application Filing
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030064735A1 (en) * | 1998-09-22 | 2003-04-03 | Spain David Stevenson | Location determination using RF fingerprinting |
US20080285530A1 (en) * | 2004-05-18 | 2008-11-20 | Cisco Systems, Inc. | Wireless Node Location Mechanism Featuring Definition of Search Region to Optimize Location Computation |
US20130162481A1 (en) | 2009-10-01 | 2013-06-27 | Parviz Parvizi | Systems and methods for calibration of indoor geolocation |
US20130281130A1 (en) * | 2011-12-16 | 2013-10-24 | Rongzhen Yang | System and method for multi-radio cloud computing for location sensing |
US20140295878A1 (en) | 2012-05-01 | 2014-10-02 | Shao-Wen Yang | Simultaneous localization and mapping using spatial and temporal coherence for indoor location |
US20140171114A1 (en) | 2012-12-14 | 2014-06-19 | Apple Inc. | Location determination using fingerprint data |
US20140179341A1 (en) | 2012-12-24 | 2014-06-26 | Jaroslaw J. Sydir | Geo-location signal fingerprinting |
US20150133148A1 (en) | 2013-05-21 | 2015-05-14 | Intel Corporation | Systems and methods for simultaneously and automatically creating databases of wifi signal information |
US20150087239A1 (en) | 2013-09-26 | 2015-03-26 | Xue Yang | Techniques for cross-device radio signal strength calibration |
US20150222372A1 (en) | 2014-02-05 | 2015-08-06 | Google Inc. | Methods and Systems for Determining Signal Strength Maps for Wireless Access Points Robust to Measurement Counts |
US20160018507A1 (en) | 2014-07-17 | 2016-01-21 | Verizon Patent And Licensing Inc. | Location tracking for a mobile device |
US20160033266A1 (en) | 2014-08-01 | 2016-02-04 | Google Inc. | Construction of a Surface of Best GPS Visibility From Passive Traces Using SLAM for Horizontal Localization and GPS Readings and Barometer Readings for Elevation Estimation |
US20160066151A1 (en) * | 2014-08-28 | 2016-03-03 | Qualcomm Incorporated | Selective crowdsourcing of location-related data |
Non-Patent Citations (13)
Title |
---|
Canadian Intellectual Property Office, International Search Report and Written Opinion for PCT/CA2017/050628 dated Aug. 30, 2017 (8 pages). |
Chan et al., Indoor Localization Using Wi-Fi Based Fingerprinting and Trilateration Techiques for LBS Applications, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XXXVIII-4/C26,7th International Conference on 3D Geoinformation, May 2012, Quebec, Canada (5 pages). |
Chen et al., Sensors ISSN 1424-8220 www.mdpi.com/journal/sensors, Article An Improved Algorithm to Generate a Wi-Fi Fingerprint Database for Indoor Positioning, Aug. 2013 (12 pages). |
Farshad et al., A Microscopic Look at WiFi Fingerprinting for Indoor Mobile Phone Localization in Diverse Environments, 2013 International Conference on Indoor Positioning and Indoor Navigation, Oct. 2013 (10 pages). |
Hossain et al., SSD: A Robust RF Location Fingerprint Addressing Mobile Devices' Heterogeneity, IEEE MASS 2007 (13 pages). |
Jiang et al., Research Article-Indoor Mobile Localization Based on Wi-Fi Fingerprint's Important Access Point, Hindawi Publishing Corporation, International Journal of Distributed Sensor Networks, vol. 2015, Article ID 429104, Mar. 2015 (9 pages). |
Jiang et al., Research Article—Indoor Mobile Localization Based on Wi-Fi Fingerprint's Important Access Point, Hindawi Publishing Corporation, International Journal of Distributed Sensor Networks, vol. 2015, Article ID 429104, Mar. 2015 (9 pages). |
Li et al., Stanford University, Indoor Positioning System Using Wifi Fingerprint, 2014 (5 pages). |
Lu et al., WiFi Fingerprint Localization in Open Space, 2013 (4 pages). |
Luo et al., Characterization of Smart Phone Received Signal Strength Indication for WLAN Indoor Positioning Accuracy Improvement, Journal of Networks, vol. 9, No. 3, Mar. 2014 (8 pages). |
Machaj et al., Rank Based Fingerprinting Algorithm for Indoor Positioning, Tampere University of Technology, 2011 (5 pages). |
Navarro et al., Wi-Fi Localization Using RSSI Fingerprinting, California Polytechnic State University, 2010 (6 pages). |
Wikipedia, Wi-Fi positioning system last modified Jan. 26, 2016 (7 pages). |
Also Published As
Publication number | Publication date |
---|---|
WO2017201621A1 (en) | 2017-11-30 |
US20170343638A1 (en) | 2017-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9958531B2 (en) | Determining a location of a wireless device using fingerprinting | |
US9609615B2 (en) | Method for building database for fingerprinting positioning and fingerprinting positioning method using the built database | |
CN110557716B (en) | Indoor positioning method based on lognormal model | |
US10349286B2 (en) | System and method for wireless positioning in wireless network-enabled environments | |
US9807549B2 (en) | Systems and methods for adaptive multi-feature semantic location sensing | |
Yu et al. | 5 G wifi signal-based indoor localization system using cluster k-nearest neighbor algorithm | |
US9485746B2 (en) | Location classification accuracy for devices inside and outside of a deployment area | |
US20170067982A1 (en) | Method and apparatus for cross device automatic calibration | |
US8738030B2 (en) | Apparatus and method for determining a correspondence of a position with a reference position | |
EP2976900B1 (en) | Building floor determination for a location based service | |
Figuera et al. | Nonparametric model comparison and uncertainty evaluation for signal strength indoor location | |
KR20140069196A (en) | Time of arrival based wireless positioning system | |
US10674312B2 (en) | Locating and tracking a wireless beacon from a wireless device | |
US9660740B2 (en) | Signal strength distribution establishing method and wireless positioning system | |
US10444319B2 (en) | Determining of model parameters for positioning purposes | |
CN107484123B (en) | WiFi indoor positioning method based on integrated HWKNN | |
US10382892B2 (en) | Bluetooth device locator | |
US11856552B2 (en) | Devices and methods for automatically labelling high-accuracy indoor localization and determining location information | |
Yiu et al. | Locating user equipments and access points using RSSI fingerprints: A Gaussian process approach | |
Atia et al. | Dynamic propagation modeling for mobile users' position and heading estimation in wireless local area networks | |
US11085991B1 (en) | Test node-based wireless positioning method and device thereof | |
Anuwatkun et al. | A diff-based indoor positioning system using fingerprinting technique and k-means clustering algorithm | |
CN111148217A (en) | Positioning method and device and electronic equipment | |
Hu et al. | Reducing Wi-Fi fingerprint collection based on affinity propagation clustering and WKNN interpolation algorithm | |
Yu et al. | An indoor localization of WiFi based on branch-bound algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: BLACKBERRY LIMITED, CANADA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:JAMPANI, KRISHNAM RAJU;REEL/FRAME:038727/0794 Effective date: 20160406 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |
|
AS | Assignment |
Owner name: MALIKIE INNOVATIONS LIMITED, IRELAND Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:BLACKBERRY LIMITED;REEL/FRAME:064104/0103 Effective date: 20230511 |
|
AS | Assignment |
Owner name: MALIKIE INNOVATIONS LIMITED, IRELAND Free format text: NUNC PRO TUNC ASSIGNMENT;ASSIGNOR:BLACKBERRY LIMITED;REEL/FRAME:064271/0199 Effective date: 20230511 |